A method and system for predicting refill rates of pharmaceuticals

By constructing a multi-dimensional index model based on the entropy weight method, eliminating interference from drug sales data, and calculating the user's independent purchase coefficient, the inaccuracy and lack of objectivity in traditional drug repurchase rate assessment are solved, thus achieving precision and objectivity in drug evaluation.

CN122243547APending Publication Date: 2026-06-19GUANGZHOU TIANCHEN HEALTH TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
GUANGZHOU TIANCHEN HEALTH TECH CO LTD
Filing Date
2026-03-10
Publication Date
2026-06-19

AI Technical Summary

Technical Problem

Traditional methods for assessing drug repurchase rates cannot accurately reflect the demand in the drug market. They are affected by differences in drug usage and dosage, individualized medication, and recommendations from store staff, resulting in subjective assessment results.

Method used

A multi-dimensional indicator model based on the entropy weight method is constructed. By acquiring drug sales data, eliminating interfering data, calculating the user's self-purchase coefficient, and using the entropy weight method to calculate the weight of each indicator, a multi-dimensional indicator model is constructed to calculate the user's self-purchase coefficient.

Benefits of technology

It improves the accuracy and objectivity of drug repurchase rate prediction, eliminates human interference, achieves objectivity and precision in drug evaluation, and supports drug replacement decisions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure FT_1
    Figure FT_1
  • Figure SMS_9
    Figure SMS_9
  • Figure SMS_24
    Figure SMS_24
Patent Text Reader

Abstract

This invention discloses a method and system for predicting drug repurchase rates. The method includes: S1. Acquiring drug sales data, including purchase behavior data, purchase group data, and sales attribute data; S2. Preprocessing the drug sales data to remove interfering data irrelevant to customer self-purchase demand assessment, obtaining valid sales data; S3. Based on the chronic disease attributes of the drug, constructing an entropy weight method multi-dimensional index model to calculate the user self-purchase coefficient; S4. Using the user self-purchase coefficient as a parameter for predicting drug repurchase rates. This invention effectively solves various defects in traditional repurchase rate assessments by constructing a multi-dimensional composite index, the user self-purchase coefficient. By constructing an entropy weight method multi-dimensional index model for prediction, it effectively improves the accuracy and objectivity of prediction, thereby providing objective and accurate data support for drug replacement decisions.
Need to check novelty before this filing date? Find Prior Art